© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 109461
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron activates on tokens that are object property or attribute names accessed via a leading dot (e.g. “.text”, “.get”, “.name”, “.value”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     imagem
    -0.07
    Founded
    -0.07
    ۱
    -0.07
    keep
    -0.07
     participate
    -0.07
    Edit
    -0.07
     textView
    -0.06
     Saudi
    -0.06
    takes
    -0.06
    II
    -0.06
    POSITIVE LOGITS
     trách
    0.07
     léka
    0.07
     satın
    0.06
     "")↵↵
    0.06
     یا
    0.06
    ・・・↵↵
    0.06
     {}↵
    0.06
    .generated
    0.06
     신규
    0.06
    ρέ
    0.06
    Activations Density 0.029%

    No Known Activations